Got rejected by YC '24 but wanted to build it anyway
Just started fundraising for seed round
471–480 of 1001 posts
Got rejected by YC '24 but wanted to build it anyway
Just started fundraising for seed round
This makes it possible to use your own, dedicated MCP server instances from, for example, n8n workflows, without thinking about infrastructure.
I’ve created an AI-powered app designed to help candidates prepare for Meta’s product manager interviews, with a focus on product execution questions. The app allows you to practice by speaking or typing your responses, then uses AI to score answers against a rubric and track your progress over time. I’m looking for beta testers—happy to share early access if you’re interested! If you are please message me.
Happy lets you spawn and control multiple Codex/Claude Code sessions in parallel. Happy Coder runs on your hardware, works from your phone and desktop, costs nothing, End to End encrypted, and permissive MIT License.
https://github.com/slopus/happy
Happy Coder is a unix style "do one thing well" project.
The goal is zero workflow disruption. I want to be able to run CLI coding agents on any internet connected computer, and control them with my phone. Happy has a command line wrapper for Codex and Claude Code that let you start a session in your terminal, and then continue it from your phone with real time sync. So type in your terminal and see it on the phone, type into your phone and see it in your terminal. So you can switch back and forth.
There is an optional voice agent some contributors have been hacking on that lets you talk to the voice agent first, and the voice agent then writes prompts for Codex/Claude Code and answers questions about what the coding agent running on your computer is doing/did. The voice agent feature is pretty neat, but in my opinion needs a bit more iteration, so any ideas or help would be awesome.
My team suffers from dependency creep. As soon as your system grows, the number of dependencies skyrockets. In Python/Javascript projects it's especially hard to determine which dependencies are not used anymore.
Pruno saves time for your team by automating this work. It's still WIP, but I'd like to get feedback. How are you dealing with your dependencies?
I live in Viet Nam, and driving through bad storms this time of year is pretty miserable, and they happen fast and are local enough that weather prediction is not terribly useful.
There are a lot of problems with EMI. Lots of ungrounded brushed motors everywhere that make the RF bits hard. If I succeed, I'll publish the PCB designs.
I've also got some educational products in production right now, about Vietnamese history. I'd share a link, but my website probably can't handle the traffic right now.
I launched Quiet UI this week: https://quietui.org/ It prioritizes accessibility, longevity, performance, and simplicity. With the autoloader, one script tag loads components dynamically without downloading the entire library. (npm also available.) Theming uses color-mix() and OKLAB to create uniform color palettes from a single CSS property. Adaptive palettes are used for dark mode. All form controls are form-associ…
"Google maps but for old maps": https://pastmaps.com This is a solo startup that I've been working on for 2 years now. It's a labor of love and I'm very lucky and thankful that it's big enough to surprisingly pay all of our bills. Still constantly feeling FOMO over all of my startup buddies working with AI and LLMs while I plug away at old maps and GIS . It gets ~80K MAUs and just slowly and consistently is growing o…
I've been building https://resolver.one - a DNS server that returns GeoIP data as TXT records. Query an IP directly as the hostname (e.g. dig TXT 8.8.8.8.rslvr.one) and get back country, ASN, etc. Always been fascinated by repurposing established protocols for unintended uses - DNS is everywhere, passes through firewalls, and has built-in caching. Seemed like a fun way to deliver location data without HTTP APIs. Supe…
Neat idea, even if it doesn't end up going anywhere. Out of curiosity, are you able to share what your source of data is? Isn't GeoIP data typically licensed?